Google Cloud Text-to-Speech API

openapi: 3.1.0
info:
  title: Google Cloud Text-to-Speech API
  description: >-
    Synthesizes natural-sounding speech from text or SSML input using Google's
    AI-powered voice synthesis technology.
  version: v1
  contact:
    name: Google Cloud
    url: https://cloud.google.com/text-to-speech
servers:
  - url: https://texttospeech.googleapis.com/v1
paths:
  /voices:
    get:
      operationId: listVoices
      summary: Google Cloud Text-To-Speech List available voices
      description: Returns a list of voices that can be used for synthesis.
      parameters:
        - name: languageCode
          in: query
          description: BCP-47 language tag to filter voices.
          schema:
            type: string
      responses:
        '200':
          description: Successful response containing available voices.
          content:
            application/json:
              schema:
                type: object
                properties:
                  voices:
                    type: array
                    items:
                      $ref: '#/components/schemas/Voice'
      tags:
        - Voices
  /text:synthesize:
    post:
      operationId: synthesizeSpeech
      summary: Google Cloud Text-To-Speech Synthesize speech
      description: Synthesizes speech from text or SSML input.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/SynthesizeSpeechRequest'
      responses:
        '200':
          description: Successful response containing synthesized audio.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/SynthesizeSpeechResponse'
      tags:
        - Text:synthesize
components:
  schemas:
    Voice:
      type: object
      properties:
        languageCodes:
          type: array
          items:
            type: string
        name:
          type: string
        ssmlGender:
          type: string
          enum:
            - SSML_VOICE_GENDER_UNSPECIFIED
            - MALE
            - FEMALE
            - NEUTRAL
        naturalSampleRateHertz:
          type: integer
    SynthesizeSpeechRequest:
      type: object
      required:
        - input
        - voice
        - audioConfig
      properties:
        input:
          type: object
          properties:
            text:
              type: string
            ssml:
              type: string
        voice:
          type: object
          properties:
            languageCode:
              type: string
            name:
              type: string
            ssmlGender:
              type: string
        audioConfig:
          type: object
          properties:
            audioEncoding:
              type: string
              enum:
                - AUDIO_ENCODING_UNSPECIFIED
                - LINEAR16
                - MP3
                - OGG_OPUS
                - MULAW
                - ALAW
            speakingRate:
              type: number
            pitch:
              type: number
            volumeGainDb:
              type: number
            sampleRateHertz:
              type: integer
    SynthesizeSpeechResponse:
      type: object
      properties:
        audioContent:
          type: string
          description: Base64-encoded audio content.
tags:
  - name: Text:synthesize
  - name: Voices